Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1840 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1908. Min Range: -1.1908

Max Act: 1.1699. Min Act: -0.0000

Data Index: 832472 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 1.1908. Min Range: -1.1908

Max Act: 1.1908. Min Act: -0.0001

Data Index: 557340 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 1.1908. Min Range: -1.1908

Max Act: 1.1214. Min Act: -0.0000

Data Index: 332334 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 1.1908. Min Range: -1.1908

Max Act: 1.1452. Min Act: -0.0001

Data Index: 719540 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 1.1908. Min Range: -1.1908

Max Act: 1.0691. Min Act: -0.0001

Data Index: 66360 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 1.1908. Min Range: -1.1908

Max Act: 0.9950. Min Act: -0.0001

Data Index: 1233547 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 1.1908. Min Range: -1.1908

Max Act: 1.0553. Min Act: -0.0001

Data Index: 716617 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 1.1908. Min Range: -1.1908

Max Act: 0.9772. Min Act: -0.0000

Data Index: 256247 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 1.1908. Min Range: -1.1908

Max Act: 1.0091. Min Act: -0.0001

Data Index: 566321 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 1.1908. Min Range: -1.1908

Max Act: 1.0028. Min Act: -0.0001

Data Index: 375893 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 1.1908. Min Range: -1.1908

Max Act: 0.9958. Min Act: -0.0001

Data Index: 698125 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 1.1908. Min Range: -1.1908

Max Act: 0.9703. Min Act: -0.0001

Data Index: 1355265 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 1.1908. Min Range: -1.1908

Max Act: 0.9401. Min Act: -0.0001

Data Index: 266455 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 1.1908. Min Range: -1.1908

Max Act: 0.9575. Min Act: -0.0001

Data Index: 1014859 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 1.1908. Min Range: -1.1908

Max Act: 0.9594. Min Act: -0.0001

Data Index: 1026672 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 1.1908. Min Range: -1.1908

Max Act: 0.9016. Min Act: -0.0001

Data Index: 319432 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 1.1908. Min Range: -1.1908

Max Act: 1.0001. Min Act: -0.0000

Data Index: 823890 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 1.1908. Min Range: -1.1908

Max Act: 0.8610. Min Act: -0.0001

Data Index: 37865 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 1.1908. Min Range: -1.1908

Max Act: 0.8815. Min Act: -0.0000

Data Index: 47416 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 1.1908. Min Range: -1.1908

Max Act: 0.8654. Min Act: -0.0001

Data Index: 1148780 (C4 (Web Text))

Max Activating Token Index: 998